Instructions to use Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free

SGLang

How to use Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free with Docker Model Runner:
```
docker model run hf.co/Bochkov/llm-fix-min-affine-recoded-minimal-code-table-free
```

llm-fix-min-affine-recoded-minimal-code-table-free

File size: 710 Bytes

f90152c

{
  "architectures": ["BVVForCausalLM"],
  "auto_map": {
    "AutoConfig": "model_binary_affine_code_n_layer_32.BVVConfig",
    "AutoModel": "model_binary_affine_code_n_layer_32.BVVForCausalLM",
    "AutoModelForCausalLM": "model_binary_affine_code_n_layer_32.BVVForCausalLM"
  },
  "model_type": "model_binary_affine_code_n_layer_32",
  "vocab_size": 65536,
  "code_bits": 16,
  "block_size": 1024,
  "d_model": 1024,
  "n_layer": 32,
  "n_head": 32,
  "code_seed": 12345,
  "min_row_weight": 4,
  "min_col_weight": 4,
  "pad_token_id": 57344,
  "zero_pad_code": true,
  "pad_id": 57344,
  "bos_token": "<s>",
  "eos_token": "</s>",
  "unk_token": "<unk>",
  "pad_token": "<pad>",
  "torch_dtype": "float32"
}